Rollup merge of #146340 - fmease:frontmatter-containment, r=fee1-dead,Urgau

Strip frontmatter in fewer places

* Stop stripping frontmatter in `proc_macro::Literal::from_str` (RUST-146132)
* Stop stripping frontmatter in expr-ctxt (but not item-ctxt!) `include`s (RUST-145945)
* Stop stripping shebang (!) in `proc_macro::Literal::from_str`
  * Not a breaking change because it did compare spans already to ensure there wasn't extra whitespace or comments (`Literal::from_str("#!\n0")` already yields `Err(_)` thankfully!)
* Stop stripping frontmatter+shebang inside some rustdoc code where it doesn't make any observable difference (see self review comments)
* (Stop stripping frontmatter+shebang inside internal test code)

Fixes https://github.com/rust-lang/rust/issues/145945.
Fixes https://github.com/rust-lang/rust/issues/146132.

r? fee1-dead

3 files changed, 22 insertions, 23 deletions

diff --git a/compiler/rustc_parse/src/lexer/mod.rs b/compiler/rustc_parse/src/lexer/mod.rs
index f5f081efc49..51019db7c00 100644
--- a/compiler/rustc_parse/src/lexer/mod.rs
+++ b/compiler/rustc_parse/src/lexer/mod.rs
@@ -45,7 +45,7 @@ pub(crate) struct UnmatchedDelim {
 }
 
 /// Which tokens should be stripped before lexing the tokens.
-pub(crate) enum StripTokens {
+pub enum StripTokens {
     /// Strip both shebang and frontmatter.
     ShebangAndFrontmatter,
     /// Strip the shebang but not frontmatter.
diff --git a/compiler/rustc_parse/src/lib.rs b/compiler/rustc_parse/src/lib.rs
index d8792d7af4c..88b67d792de 100644
--- a/compiler/rustc_parse/src/lib.rs
+++ b/compiler/rustc_parse/src/lib.rs
@@ -54,29 +54,18 @@ pub fn unwrap_or_emit_fatal<T>(expr: Result<T, Vec<Diag<'_>>>) -> T {
     }
 }
 
-/// Creates a new parser from a source string. On failure, the errors must be consumed via
-/// `unwrap_or_emit_fatal`, `emit`, `cancel`, etc., otherwise a panic will occur when they are
-/// dropped.
-pub fn new_parser_from_source_str(
-    psess: &ParseSess,
-    name: FileName,
-    source: String,
-) -> Result<Parser<'_>, Vec<Diag<'_>>> {
-    let source_file = psess.source_map().new_source_file(name, source);
-    new_parser_from_source_file(psess, source_file, StripTokens::ShebangAndFrontmatter)
-}
-
-/// Creates a new parser from a simple (no shebang, no frontmatter) source string.
+/// Creates a new parser from a source string.
 ///
 /// On failure, the errors must be consumed via `unwrap_or_emit_fatal`, `emit`, `cancel`,
 /// etc., otherwise a panic will occur when they are dropped.
-pub fn new_parser_from_simple_source_str(
+pub fn new_parser_from_source_str(
     psess: &ParseSess,
     name: FileName,
     source: String,
+    strip_tokens: StripTokens,
 ) -> Result<Parser<'_>, Vec<Diag<'_>>> {
     let source_file = psess.source_map().new_source_file(name, source);
-    new_parser_from_source_file(psess, source_file, StripTokens::Nothing)
+    new_parser_from_source_file(psess, source_file, strip_tokens)
 }
 
 /// Creates a new parser from a filename. On failure, the errors must be consumed via
@@ -87,6 +76,7 @@ pub fn new_parser_from_simple_source_str(
 pub fn new_parser_from_file<'a>(
     psess: &'a ParseSess,
     path: &Path,
+    strip_tokens: StripTokens,
     sp: Option<Span>,
 ) -> Result<Parser<'a>, Vec<Diag<'a>>> {
     let sm = psess.source_map();
@@ -110,7 +100,7 @@ pub fn new_parser_from_file<'a>(
         }
         err.emit();
     });
-    new_parser_from_source_file(psess, source_file, StripTokens::ShebangAndFrontmatter)
+    new_parser_from_source_file(psess, source_file, strip_tokens)
 }
 
 pub fn utf8_error<E: EmissionGuarantee>(
@@ -172,6 +162,9 @@ fn new_parser_from_source_file(
     Ok(parser)
 }
 
+/// Given a source string, produces a sequence of token trees.
+///
+/// NOTE: This only strips shebangs, not frontmatter!
 pub fn source_str_to_stream(
     psess: &ParseSess,
     name: FileName,
@@ -179,13 +172,16 @@ pub fn source_str_to_stream(
     override_span: Option<Span>,
 ) -> Result<TokenStream, Vec<Diag<'_>>> {
     let source_file = psess.source_map().new_source_file(name, source);
-    // used mainly for `proc_macro` and the likes, not for our parsing purposes, so don't parse
-    // frontmatters as frontmatters, but for compatibility reason still strip the shebang
+    // FIXME(frontmatter): Consider stripping frontmatter in a future edition. We can't strip them
+    // in the current edition since that would be breaking.
+    // See also <https://github.com/rust-lang/rust/issues/145520>.
+    // Alternatively, stop stripping shebangs here, too, if T-lang and crater approve.
     source_file_to_stream(psess, source_file, override_span, StripTokens::Shebang)
 }
 
-/// Given a source file, produces a sequence of token trees. Returns any buffered errors from
-/// parsing the token stream.
+/// Given a source file, produces a sequence of token trees.
+///
+/// Returns any buffered errors from parsing the token stream.
 fn source_file_to_stream<'psess>(
     psess: &'psess ParseSess,
     source_file: Arc<SourceFile>,
diff --git a/compiler/rustc_parse/src/parser/tests.rs b/compiler/rustc_parse/src/parser/tests.rs
index a6e7266e71b..e645fb47b9e 100644
--- a/compiler/rustc_parse/src/parser/tests.rs
+++ b/compiler/rustc_parse/src/parser/tests.rs
@@ -22,6 +22,7 @@ use rustc_span::{
 };
 use termcolor::WriteColor;
 
+use crate::lexer::StripTokens;
 use crate::parser::{ForceCollect, Parser};
 use crate::{new_parser_from_source_str, source_str_to_stream, unwrap_or_emit_fatal};
 
@@ -35,6 +36,7 @@ fn string_to_parser(psess: &ParseSess, source_str: String) -> Parser<'_> {
         psess,
         PathBuf::from("bogofile").into(),
         source_str,
+        StripTokens::Nothing,
     ))
 }
 
@@ -2240,7 +2242,7 @@ fn parse_item_from_source_str(
     source: String,
     psess: &ParseSess,
 ) -> PResult<'_, Option<Box<ast::Item>>> {
-    unwrap_or_emit_fatal(new_parser_from_source_str(psess, name, source))
+    unwrap_or_emit_fatal(new_parser_from_source_str(psess, name, source, StripTokens::Nothing))
         .parse_item(ForceCollect::No)
 }
 
@@ -2520,7 +2522,8 @@ fn ttdelim_span() {
         source: String,
         psess: &ParseSess,
     ) -> PResult<'_, Box<ast::Expr>> {
-        unwrap_or_emit_fatal(new_parser_from_source_str(psess, name, source)).parse_expr()
+        unwrap_or_emit_fatal(new_parser_from_source_str(psess, name, source, StripTokens::Nothing))
+            .parse_expr()
     }
 
     create_default_session_globals_then(|| {